Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    গ্রস্ত
    0.84
     Grange
    0.82
     SAINT
    0.79
     जिस
    0.77
    曛
    0.76
    ここは
    0.76
    ሰው
    0.76
     இன்னொரு
    0.75
    ี่ยว
    0.74
     datum
    0.74
    POSITIVE LOGITS
    కీ
    0.79
     Turing
    0.70
     reveals
    0.67
     führte
    0.66
    ]["
    0.66
     `"
    0.65
    }{
    0.63
    =="
    0.63
    gel
    0.63
    !"
    0.63
    Act Density 0.079%

    No Known Activations